As an emerging computing paradigm, Computing Power Networks (CPNs) are dedicated to coordinating and managing network resources and computing resources to achieve interconnectivity in computing power perception. Efficient collaborative computing of massive data can be achieved through the scheduling function of CPNs. However, existing scheduling research mainly focuses on selecting network links and computing nodes, lacking consideration for task execution after scheduling, which may degrade the Quality of Service (QoS), leading to widespread failures and significant losses. To address this issue, we design a priority-aware preemptive task scheduling (P2TS) strategy for CPNs to jointly optimize task scheduling and execution in terms of success rate, average processing delay, and load balancing. Specifically, at the execution level, we propose a priority-aware preemptive mechanism (P2M) to optimize post-scheduling task execution. Then, at the scheduling level, we apply deep reinforcement learning (DRL) to optimize the scheduling process supporting the P2M in CPNs. A series of simulations are conducted to demonstrate the superiority of our strategy.

The exponential increase in connected user devices poses scalability challenges for centralized cloud computing. Mobile Edge Computing (MEC) and Fog Computing alleviate latency by deploying computation and storage resources closer to end-users. However, due to the resource limitations, heterogeneity, and dispersed nature of edge servers, there is a need to jointly optimize service caching and application placement strategies to enhance service quality. Given the widespread use of containerized services at the edge, we propose a distributed caching scheme that allows all edge nodes to cache services at the granularity of container image layers. This collaborative caching approach reduces the real-time latency, bandwidth consumption, and caching costs associated with retrieving and initializing applications. Additionally, to address the variability in application popularity across different edge regions, we model application popularity using a Zipf distribution and construct a multi-slot joint optimization model for caching and deployment decisions based on deployment cost, application startup time, and average delay. We then propose a two-stage optimization method to solve this model, demonstrating through comparison with centralized and P2P models the effectiveness of the proposed approach.

As generative artificial intelligence (GAI) advances, technologies such as diffusion models provide the foundation for end-edge collaborative computing. Current plug-in network AI capabilities require improvements in efficiency and other aspects. Fortunately, the 6G native AI wireless network offers integrated management capabilities for AI tasks and multidimensional resources, enabling the delivery of high-quality AI services. Therefore, this paper considers an AI service quality optimization scheme for GAI inference in native AI wireless networks, allowing for appropriate resource allocation, expected content quality and inference split point selection. To provide results without subjective preference information, we establish a three-objective integer programming problem to optimize the performance of task delay, energy consumption, and content generation quality. Then, an ASQO algorithm is used to obtain the approximate solution of the three-dimensional Pareto optimal set. Finally, we conduct simulations to verify the feasibility and performance of the proposed scheme.

Toward the sixth generation (6G) Internet of vehicles (IoV) networks, key challenges such as massive connectivity, high mobility and superior energy efficiency have driven the development of advanced wireless technologies. Native artificial intelligence (AI) is expected to support diverse vertical industries and offer numerous emerging AI services for 6G. However, how to efficiently process AI services and improve resource utilization while ensuring quality of service is still a challenging problem. In this paper, non-orthogonal multiple access (NOMA) is applied in the designed three-layer IoV network architecture. Then, an energy efficiency maximization problem is formulated by jointly optimizing NOMA transmission power and AI task deployment decisions. Third, a two-level iterative algorithm is proposed using the Dinkelbac’s method. Simulation results verify that our proposed algorithm outperforms benchmarks in terms of energy efficiency.

In this paper, we propose an innovative architecture for sharing intelligence in low earth orbit (LEO) satellite edge computing networks. Specifically, we adopt the sharing of intel-ligence to satellites via ground stations to improve the response speed of satellites in processing intelligent services. Considering the burden of frequent transmission of intelligent models over unstable ground-satellite links, the satellites share intelligence with each other in the coalition, which greatly reduces the service response delay. In addition, considering the poor generalization of pre-trained intelligent models transmitted by ground stations, we design a model aggregation scheme with differentiated weights. Each coalition appoints a coalition center satellite, tasked with aggregating models and re-sharing them to individual satellites, thereby enhancing model performance. Then, we propose two low-time complexity algorithms to solve the above problems. Finally, the effectiveness and superiority of the proposed schemes are verified through extensive simulations.

With the rise of the computing power network (CPN), which integrate edge computing, cloud computing, and network infrastructure, replicated computing services are increasingly distributed to meet user demands for location-independent, reliable, and low latency services. Service anycast forwarding coordinates distributed service instances by binding them to a unified identifier and dynamically routing requests to the optimal instance. However, challenges such as varying user demand distribution, network complexity, and service instance heterogeneity complicate balanced service forwarding. To address these, we propose an SDN-based service anycast forwarding mechanism for CPN (SA-CPN). In the data plane, a cyclic forwarding queue efficiently maps weighted strategies and selects instances for each service request, improving policy performance. In the control plane, an optimal transport model balances network and computation latency based on service instance capabilities. We further design an optimal transport-based service anycast forwarding algorithm (OTSAF) using Sinkhorn iterations. Our implementation of SA-CPN in a real system shows that OTSAF consistently outperforms four baseline methods across various performance metrics.

Industrial Cyber-Physical Systems (CPS) have made significant strides in recent years, driving the future of manufacturing. However, for further advancement in Cloud-Fog Automation (CFA), several challenges remain: rigid sensor sampling, inflexible communication configurations, insufficient coordination between cloud and fog resources, and a lack of integration between sensing, communication, and computing for effective control. To address these issues, this article presents SeCo4, an intelligent control framework for the co-design of sensing, communication, and computing in industrial CPS. The SeCo4 optimization problem is analyzed and divided into two sub-problems: a multi-controller cloud resource competition problem, formulated with a combinatorial auction to enable multi-controller competition for additional cloud resources and improve control performance; and a joint resource optimization problem for sensing, communication, and computing, modeled using a Mixed Integer Programming (MIP) problem to minimize control costs. Given the interdependence of these sub-problems, a hierarchical solution based on the online matching mechanism and the heuristic approach is developed to iteratively find the optimal solution. Finally, extensive simulations demonstrate the effectiveness and superiority of the proposed approach.

This paper establishes a dual-timescale framework for joint resource slicing and task scheduling in satellite edge computing (SEC) networks. Specifically, to capture network dynamics and task stochasticity at small timescales, we formulate the task scheduling problem as a Markov decision process (MDP) to minimize task delay, network energy consumption, and packet loss. We design a deep reinforcement learning-assisted task scheduling (DRTS) algorithm inspired by the soft actor-critic (SAC) algorithm to learn the scheduling policy. Task processing performance is affected by communication and computing re-sources allocated to respective resource slices. Thus, considering that frequent resource slicing has a significant management over-head, we further optimize resource slices on a larger timescale. To obtain a policy with low complexity, we propose a greedy-based heuristic algorithm. A hierarchical solution is constructed to find the optimal solution due to the correlation between the two timescale problems. Finally, to validate the effectiveness and superiority of the proposed scheme, extensive simulations are performed.

In industrial manufacturing, visual anomaly detection is critical for maintaining product quality by detecting and preventing production anomalies. Anomaly detection methods based on knowledge distillation demonstrate promising performance in addressing the unpredictability and diversity of anomalies. However, they suffer from a lack of effective guidance from anomaly-free priors when handling anomalous features and underutilize multi-scale features during the segmentation scoring stage, yielding suboptimal detection results. To alleviate these issues, we propose an Anomaly-free Prior Guided knowledge distillation (APG) for industrial anomaly detection. Firstly, it filters the abnormal features by training the de-noising target network with knowledge distillation structure. Concurrently, we propose the Prior Perception Propagation Module (P3M), which extracts more efficient anomaly-free features by imposing constraints on anomalous features. Secondly, we propose the Multi-scale Prior Guided Fusion Module (MPGFM) to improve anomaly detection accuracy by utilizing anomaly-free features from the target network as priors to guide the generation and fusion of cross-scale differential features. Finally, the Global Perception Enhancement Module (GPEM) is proposed to construct an anomaly scoring network, leveraging comprehensive scene features to enhance the detection and localization performance of numerous small-target anomalies in industrial manufacturing. Extensive experiments on the MVTecAD and BTAD datasets show that the proposed method demonstrates a consistent and significant outperformance against competing methods.

In this paper, we establish a two-timescale framework for the joint service deployment and task scheduling problem in satellite edge computing networks.We aim to optimize the computing performance of networks with diverse quality-of-service (QoS) guarantees for computing tasks. Specifically, to capture the small-timescale network dynamics and task randomness, we formulate the task scheduling problem as a constrained Markov decision process (CMDP) to minimize the energy consumption, load imbalance and packet loss of networks while ensuring the long-term delay. The Lyapunov technique is employed to deal with the delay constraints. A soft actor-critic (SAC)-based deep reinforcement learning (DRL) framework is designed to learn the stationary scheduling policy. We further explore the significant impact of deploying diverse services on the performance of task scheduling in satellite edge computing. Considering that frequent deployment of services will incur huge deployment overhead, we optimize the service deployment on a larger timescale. The optimization problem is modeled as an integer programming problem to improve the service capability of networks and reduce service deployment costs. A heuristic-based atomic orbital search (AOS) approach is proposed to obtain the superior policy with low complexity. Due to the correlation between the problems of two timescales, a hierarchical solution is constructed to iteratively find the excellent solution. Finally, extensive simulations are conducted to validate the effectiveness and superiority of the proposed scheme.

In this paper, we optimize network computational performance and ensure diverse quality of service (QoS) for tasks by developing a dual-timescale joint optimization framework for satellite-terrestrial integrated edge computing networks (STECN). In our architecture, STECN can handle intelligent tasks for the Internet of remote things (IoRT) devices based on multiple configured applications deployed. Specifically, we formulate task scheduling as a Markov decision process (MDP) to minimize network energy consumption and task processing delay at small timescales. A deep reinforcement learning (DRL) framework is designed for policy learning. Recognizing the impact of resource slicing on task scheduling in STECN and the deployment overhead from frequent changes, we further optimize resource slicing at larger timescales. To enhance network service capability under dynamic demand, we establish a resource slice gap index, characterizing the difference between actual resources and service demand. By a heuristic-based artificial electric field (AEF) approach, we obtain an optimal strategy with low complexity. Considering the correlation between two timescales, the optimal solution is found by iteratively constructing a hierarchical solution. In addition, to guarantee the global load balancing of the network, we introduce a self-attention mechanism, which allows the knowledge of other satellites to be taken into account when slicing the satellite resources. Finally, extensive simulations confirm the effectiveness and superiority of the proposed scheme.

In the era driven by big data and algorithms, the efficient collaboration of pervasive computing power is crucial for rapidly meeting computing demands and enhancing resource utilization. However, current mainstream end-edge-cloud collaboration faces challenges of computing isolation, adversely affecting resource efficiency and user experience. The Computing Power Network (CPN) is a novel architecture designed to sense and collaborate ubiquitous computing resources through networks. Nevertheless, the expansion of its scope and the integration of networks complicate task scheduling. To address this, we design a collaborative scheduling system that considers the joint selection of computing nodes and network links, aiming to reduce delay, enhance reliability, and ensure long-term load balance. First, we propose a delay-prioritized reliable scheduling policy based on a dual-priority mechanism for forwarding and computing. Second, we define the scheduling problem as a Constrained Markov Decision Process (CMDP) and introduce Lyapunov optimization to transform constraints into instantaneous optimizations, achieving a long-term balanced load of computing and network resources. Lastly, we employ an enhanced Deep Reinforcement Learning (DRL) approach to solve the problem. Performance evaluation demonstrates that compared to standard DRL, the proposed algorithm effectively reduces delay and improves reliability while maintaining long-term load balance, resulting in an overall performance improvement of 54.7%.

Edge intelligence is emerging as a new interdiscipline to push learning intelligence from remote centers to the edge of the network. However, with its widespread deployment, new challenges arise in terms of training efficiency and service of quality (QoS). Massive repetitive model training is ubiquitous due to the inevitable needs of users for the same types of data and training results. Additionally, a smaller volume of data samples will cause the over-fitting of models. To address these issues, driven by the Internet of intelligence, this paper proposes a distributed edge intelligence sharing scheme, which allows distributed edge nodes to quickly and economically improve learning performance by sharing their learned intelligence. Considering the time-varying edge network states including data collection states, computing and communication states, and node reputation states, the distributed intelligence sharing is formulated as a multi-agent Markov decision process (MDP). Then, a novel collective deep reinforcement learning (CDRL) algorithm is designed to obtain the optimal intelligence sharing policy, which consists of local soft actor-critic (SAC) learning at each edge node and collective learning between different edge nodes. Simulation results indicate our proposal outperforms the benchmark schemes in terms of learning efficiency and intelligence sharing efficiency.

In this article, we propose a multilayer Ka/Q-band satellite–terrestrial integrated network for the Internet of Remote Things (IoRT) to achieve a high transmission rate with communication robustness in dynamic network environments. Under this architecture, we investigate how to jointly manage the offloading path selection and resource allocation to offload computation-intensive and delay-sensitive tasks in the IoRT. Considering continuous low earth orbit (LEO) satellite movements and Markovian rainfall changes, the computation offloading problem is described as a Markov decision process (MDP) formulation with the objective of maximizing the number of offloaded tasks with satisfied delay requirements and minimizing the power consumption of the LEO satellites. A deep reinforcement learning (DRL) approach is leveraged to make optimal decisions by taking account of dynamic queues of IoRT devices, channel conditions that vary with rainfall intensities and satellite positions, and computing capabilities of ground stations. Extensive simulations are conducted to validate the effectiveness and superiority of our proposed scheme.

By delegating the infrastructure management, such as provisioning or scaling to third-party providers, serverless edge computing has recently been widely adopted in several applications, especially Internet of Things (IoT) applications. Task scheduling is a critical issue in serverless edge computing as it significantly impacts the quality of user experience. In contrast to the centralized scheduling in the cloud center, serverless edge task scheduling is more challenging due to the heterogeneous and resource-constrained nature of edge resources. This article aims to study the distributed task scheduling for the IoT in serverless edge computing networks, in which heterogeneous serverless edge computing nodes are rational individuals with interests to optimize their own scheduling utility while the nodes only have access to local observations. The task scheduling competition process is formulated as a partially observable stochastic game (POSG) to enable serverless edge computing nodes to noncooperatively schedule tasks and allocate computing resources depending on their locally observed system state, which takes into account the associated task generation state, data queue state, communication channel state, and previous computing resource allocation state. To solve the proposed POSG and deal with the partial observability, a multiagent task scheduling algorithm based on the dueling double deep recurrent$Q$-network (D3RQN) method is developed to approximate the optimal task scheduling and resource allocation solution. Finally, extensive simulation experiments are conducted to validate the effectiveness and superiority of the proposed scheme.

C programming language never performs automatic bounds checking in order to speed up execution. But bounds checking is absolutely necessary in any program. Because if a variable is out-of-bounds, some serious errors may occur during execution, such as endless loop or buffer overflows. When there are arrays used in a program, the index of an array must be within the boundary of the array. But programmers always miss the array bounds checking or do not perform a correct array bounds checking. In this paper, we perform static analysis based on taint analysis and data flow analysis to detect which arrays do not have correct array bounds checking in the program. And we implement an automatic static tool, Carraybound. And the experimental results show that Carraybound can work effectively and efficiently.